Home

In this paper, we propose a novel end-to-end neural network to reconstruct high resolution images from non-regularly sampled sensor data. The network is a concatenation of a locally fully connected reconstruction network (LFCR) and a standard VDSR network. Altogether, using a three-quarter sampling... Continue

We propose faster consistency checking methods as well as a novel recursive FSR that uses the projected pixels different than in literature and can handle dynamic masks. Altogether, we are able to significantly increase the reconstruction quality by +1.01 dB compared to the state-of-the-art recursi... Continue

After more than one year, we finally opened our premises for students! This means that from now on, students may use the PCs in the student's lab on the 5th floor and in the lab room on the 6th floor. In addition, we hope to be able to have live lectures again in the lecture hall on the 5th floor be... Continue

In July, we hopefully finished the last semester under Corona conditions. We really hope and wish that in the next semester, we can welcome you, the students, back at our chair and in our lectures! Additionally, as a special activity, we would like to mention that we actively took part in the las... Continue

From now on, there will be a regular post on the latest news from the LMS. In this first post we report from our activites on international conferences and we say hello to our new co-workers. Although we are still in times of a pandemic, we visited various conferences in June. We virtually took p... Continue

We are currently searching for an outstanding Master graduate in electrical engineering (with strong background in signal processing). We offer a full-time position to do research in the field of video processing. If you are interested, please send a full application to Prof. Dr.-Ing. André Kaup (an... Continue

We propose a novel viewport-adaptive motion compensation technique for fisheye video that reaches average gains of +2.40 dB in terms of PSNR compared to the state of the art in fisheye motion compensation. These gains are achieved by respresenting motion on different motion planes in 3D space. Continue

We are now presenting the new layout for our website! It is more attractive and intuitive. At the same time, we present our new co-worker: The robot pepper that is supporting our research in audio processing.  Continue

Deep Learning in Image and Video Processing   Prof. Dr.-Ing. André Kaup Friedrich-Alexander University Prof. Dr.-Ing. Bin Yang University of Stuttgart Prof. Dr.-Ing. Eckehard Steinbach (Guestlecturer) Technical University of Munich Within this course, we want to ex... Continue

In recognition of outstanding achievements in the broad field of Signal Processing, the European Association for Signal Processing (EURASIP) elevates each year a select group of up to a maximum of four scholars to “EURASIP Fellow”, the Association's most prestigious honor. As one of the EURASIP Fell... Continue

As a former Vice President of the IEEE Signal Processing Society, Walter Kellermann has been re-elected to serve on the Society's Nominations and Appointments Committee Nominations and Appointments Committee for the two-year term 2021-2022. Continue

The conference paper entitled „Enhanced Image Reconstruction From Quarter Sampling Measurements Using an Adapted Very Deep Super Resolution Network“ by Simon Grosche, Kristian Fischer, Fabian Brand, Jürgen Seiler und André Kaup was awarded with a Top Viewed Q&A Paper Award (1st place) at the IEE... Continue

The conference article "Key-point Agnostic Frequency-Selective Mesh-to-Grid Resampling using Spectral Weighting" by Viktoria Heimann, Nils Genser, and André Kaup is awarded as Best Student Paper at the IEEE 22nd International Workshop on Multimedia Signal Processing. Continue

The results of the exam 'Image and Video Compression (IVC)' are now available on 'meinCampus'. An inspection of the exam will be possible on 11.08.2020 between 9:00 - 11:00 am in room 06.025. Please arrange a personal appointment previously. Continue